SOURCE-LINKED INTELLIGENCE

SPD: Single Pass Decoding for Generative Reranking

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Large language models (LLMs) achieve state-of-the-art generative ranking quality, but the ranking they produce must be decoded, and autoregressive decoding spends one sequential forward pass per emitted token. We observe that the only tokens a ranker must emit are the $N$ ordinal values naming the items in ranked order, and that this narrow, permutation-structured output format admits decoding strategies which are much more efficient than left-to-right generation. We introduce SPD (Single Forward Pass), a format-specialized decoding strategy that decodes all $N$ ordinals in $O(1)$ forward pass

Read original source ↗ Open in workspace

recordType

paper

region

Global